Free Databricks Databricks-Machine-Learning-Associate Exam Dumps Questions & Answers

A data scientist has developed a random forest regressor rfr and included it as the final stage in a Spark MLPipeline pipeline. They then set up a cross-validation process with pipeline as the estimator in the following code block:

Which of the following is a negative consequence of including pipeline as the estimator in the cross-validation process rather than rfr as the estimator?

• A.  The process will be unable to parallelize tuning due to the distributed nature of pipeline
• B.  The process will have a longer runtime because all stages of pipeline need to be refit or retransformed with each mode
• C.  The process will leak data prep information from the validation sets to the training sets for each model
• D.  The process will leak data from the training set to the test set during the evaluation phase

A machine learning engineer is trying to scale a machine learning pipeline by distributing its single-node model tuning process. After broadcasting the entire training data onto each core, each core in the cluster can train one model at a time. Because the tuning process is still running slowly, the engineer wants to increase the level of parallelism from 4 cores to 8 cores to speed up the tuning process. Unfortunately, the total memory in the cluster cannot be increased.
In which of the following scenarios will increasing the level of parallelism from 4 to 8 speed up the tuning process?

• A.  When the data is particularly long in shape
• B.  When the model is unable to be parallelized
• C.  When the entire data can fit on each core
• D.  When the tuning process in randomized
• E.  When the data is particularly wide in shape

A data scientist is developing a single-node machine learning model. They have a large number of model configurations to test as a part of their experiment. As a result, the model tuning process takes too long to complete. Which of the following approaches can be used to speed up the model tuning process?

• A.  Enable autoscaling clusters
• B.  Implement MLflow Experiment Tracking
• C.  Scale up with Spark ML
• D.  Parallelize with Hyperopt

Which of the following is a benefit of using vectorized pandas UDFs instead of standard PySpark UDFs?

• A.  The vectorized pandas UDFs process data in memory rather than spilling to disk
• B.  The vectorized pandas UDFs work on distributed DataFrames
• C.  The vectorized pandas UDFs allow for pandas API use inside of the function
• D.  The vectorized pandas UDFs process data in batches rather than one row at a time
• E.  The vectorized pandas UDFs allow for the use of type hints

A data scientist wants to use Spark ML to impute missing values in their PySpark DataFrame features_df. They want to replace missing values in all numeric columns in features_df with each respective numeric column's median value.
They have developed the following code block to accomplish this task:

The code block is not accomplishing the task.
Which reasons describes why the code block is not accomplishing the imputation task?

• A.  It does not impute both the training and test data sets.
• B.  It does not fit the imputer on the data to create an ImputerModel.
• C.  The fit method needs to be called instead of transform.
• D.  The inputCols and outputCols need to be exactly the same.